BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-2022//speaker//U397XP
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-2022-ZZGNXV@talks.staging.osgeo.org
DTSTART;TZID=CET:20220824T113000
DTEND;TZID=CET:20220824T120000
DESCRIPTION:Acquiring and labeling geospatial data for training machine lea
 rning models is a time-consuming and expensive process. It is made even mo
 re difficult by the lack of specialized open-source tools for dealing with
  the idiosyncrasies of geospatial data. At Azavea\, we have encountered bo
 th of these problems before. In this talk\, we will present a solution tha
 t incorporates our geospatial annotation platform\, GroundWork (https://gr
 oundwork.azavea.com)\, with our open-source deep learning framework\, Rast
 er Vision (https://rastervision.io)\, to provide a human-in-the-loop activ
 e learning workflow. This workflow allows labelers to immediately see the 
 effect of their created labels on the model’s performance\, thus speedin
 g up the labeling-training-labeling cycle and making the connection betwee
 n the AI and human GIS data labelers easy and seamless. \n\nThis talk will
  extend the hands-on experience introduced in last year’s “Human-in-th
 e-loop Machine Learning with GroundWork and STAC'' FOSS4G workshop. We wil
 l present an enhanced active-learning workflow that allows labelers to tra
 in a model and see predictions on-the-fly as they create labels in GroundW
 ork. The model-training and predictions will be handled by Raster Vision. 
 This workflow will give the labelers a clear view of the model’s current
  strength and weaknesses at all times\, and thus allow them to direct thei
 r labeling efforts more efficiently. Newly created labels will propagate b
 ack to the AI model in real time\, and an asynchronous job will continue t
 o refine the model and predictions. This loop is backed by the open-source
  Raster Foundry (https://rasterfoundry.azavea.com) and Franklin (https://a
 zavea.github.io/franklin) APIs\, and is compliant with the STAC (https://s
 tacspec.org) and OGC Features (https://www.ogc.org/standards/ogcapi-featur
 es) open standards.
DTSTAMP:20260403T222553Z
LOCATION:Room 4
SUMMARY:Human-in-the-loop Machine Learning with Realtime Model Predictions 
 using GroundWork and Raster Vision - Aaron Su\, Adeel Hassan\, Simon Kasse
 l
URL:https://talks.staging.osgeo.org/foss4g-2022/talk/ZZGNXV/
END:VEVENT
END:VCALENDAR